© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 62056 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
62056

INDEX

Explanations

lists, numbers, letters

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf

Configuration

Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

via

-0.13

Via

-0.12

via

-0.12

Via

-0.12

-await

-0.11

_via

-0.10

VIA

-0.10

xo

-0.09

ERT

-0.09

zo

-0.09

POSITIVE LOGITS

ë¶ĢíĦ°

0.19

èĩ³

0.17

 aÅ¾

0.16

etc

0.15

 through

0.15

åĪ°

0.13

ï½ŀ

0.13

 ÎŃÏīÏĤ

0.12

?,?,?,?,

0.12

 åĪ°

0.12

Activations Density 0.164%

No Known Activations